CN112990562A - Forest fire prevention grade prediction algorithm based on community characteristics - Google Patents
Forest fire prevention grade prediction algorithm based on community characteristics Download PDFInfo
- Publication number
- CN112990562A CN112990562A CN202110244701.XA CN202110244701A CN112990562A CN 112990562 A CN112990562 A CN 112990562A CN 202110244701 A CN202110244701 A CN 202110244701A CN 112990562 A CN112990562 A CN 112990562A
- Authority
- CN
- China
- Prior art keywords
- fire
- forest
- obtaining
- index
- fire prevention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000002265 prevention Effects 0.000 title claims abstract description 46
- 238000012544 monitoring process Methods 0.000 claims abstract description 61
- 238000011156 evaluation Methods 0.000 claims description 9
- 230000003247 decreasing effect Effects 0.000 claims description 6
- 230000009970 fire resistant effect Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 238000000034 method Methods 0.000 abstract 3
- 238000004364 calculation method Methods 0.000 abstract 1
- 241000894007 species Species 0.000 description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 239000002028 Biomass Substances 0.000 description 1
- 238000003915 air pollution Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/005—Fire alarms; Alarms responsive to explosion for forest fires, e.g. detecting fires spread over a large or outdoors area
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Emergency Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A forest fire prevention grade prediction algorithm based on community characteristics relates to a forest fire prevention grade prediction technology and aims to solve the problem that the prediction accuracy is low due to the fact that fire risk prediction of the existing national weather bureau is finished only by means of weather monitoring data. According to the method, the community characteristics of the forest are combined with meteorological monitoring data, the comprehensive fire danger index is finally obtained through the calculation of the forest type fire danger index, the average tree age fire danger index, the forest stand density fire danger index and the meteorological monitoring fire danger index, and finally the forest fire prevention grade is predicted by utilizing the comprehensive fire danger index. The method has the advantage of increasing the prediction precision. The method is suitable for predicting the forest fire prevention level in the county and has guiding significance for forest fire prevention in the county and the county.
Description
Technical Field
The invention relates to a forest fire prevention grade prediction technology.
Background
The forest fire is a natural disaster with strong burst, great destructiveness and difficult treatment and rescue, the forest fire burns trees, directly reduces the forest area, seriously destroys the forest structure and the forest environment, easily causes air pollution, water and soil loss and forest biomass reduction, even threatens the life and property safety of people and easily causes people and livestock casualties; therefore, forest fire prevention is not only an urgent requirement for protecting natural resources, protecting ecological environment and maintaining social stability of forest areas; at present, the forecast of forest fire is mainly the fire forecast of the national weather bureau, the fire forecast of the national weather bureau is carried out according to the weather monitoring data of weather stations of all regions, the fire forecast of the national scale has reference significance only, but has no guiding significance for the forecast of forest fire prevention levels in county and county areas, and meanwhile, the fire forecast of the national weather bureau is carried out only by depending on the weather monitoring data, so the accuracy of the fire forecast of the national weather bureau is low.
Disclosure of Invention
The invention aims to solve the problem that the prediction accuracy is low because the fire risk prediction of the existing national weather bureau is finished only by depending on weather monitoring data, and provides a forest fire prevention grade prediction algorithm based on community characteristics.
The forest fire-prevention grade prediction algorithm based on community characteristics is used for predicting the fire-prevention grade of a monitored area;
the forest fire prevention grade prediction algorithm comprises the following steps:
step one, acquiring the proportion of fire-resistant tree species in the tree species in a monitoring area, and obtaining the fire risk index of the tree species according to the proportion of the fire-resistant tree species;
step two, obtaining the average tree age of the monitoring area, and obtaining an average tree age fire risk index according to the average tree age;
step three, acquiring the forest stand density of the monitoring area, and obtaining a forest stand density fire risk index according to the forest stand density;
acquiring meteorological monitoring data of a monitoring area, and obtaining a meteorological monitoring fire risk index according to the meteorological monitoring data;
step five, the forest type fire risk index obtained in the step one is simultaneously summed with the average tree age fire risk index obtained in the step two, the forest stand density fire risk index obtained in the step three and the weather monitoring fire risk index obtained in the step four to obtain a comprehensive fire risk index;
and step six, predicting the forest fire prevention grade according to the comprehensive fire danger index obtained in the step five.
The invention has the beneficial effects that: the forest fire prevention grade prediction algorithm combines the community characteristics of the forest with meteorological monitoring data, calculates the forest type fire danger index, the average tree age fire danger index, the forest stand density fire danger index and the meteorological monitoring fire danger index respectively to finally obtain the comprehensive fire danger index, and predicts the forest fire prevention grade by using the comprehensive fire danger index, wherein the comprehensive fire danger index combines the community characteristics of the forest, increases the prediction precision, is suitable for forest fire prevention grade prediction in county areas, and has guiding significance on forest fire prevention in county areas.
Drawings
Fig. 1 is a block diagram of a forest fire-prevention level prediction algorithm based on community characteristics according to a specific embodiment.
Detailed Description
The first embodiment is as follows: the embodiment is described with reference to fig. 1, and the forest fire-prevention level prediction algorithm based on community characteristics is used for predicting the fire-prevention level of a monitored area;
the forest fire prevention grade prediction algorithm comprises the following steps:
step one, acquiring the proportion of fire-resistant tree species in the tree species in a monitoring area, and obtaining the fire risk index of the tree species according to the proportion of the fire-resistant tree species;
step two, obtaining the average tree age of the monitoring area, and obtaining an average tree age fire risk index according to the average tree age;
step three, acquiring the forest stand density of the monitoring area, and obtaining a forest stand density fire risk index according to the forest stand density;
acquiring meteorological monitoring data of a monitoring area, and obtaining a meteorological monitoring fire risk index according to the meteorological monitoring data;
step five, the forest type fire risk index obtained in the step one is simultaneously summed with the average tree age fire risk index obtained in the step two, the forest stand density fire risk index obtained in the step three and the weather monitoring fire risk index obtained in the step four to obtain a comprehensive fire risk index;
and step six, predicting the forest fire prevention grade according to the comprehensive fire danger index obtained in the step five.
The second embodiment is as follows: in this embodiment, the forest fire-prevention-level prediction algorithm based on community characteristics is further defined in the first embodiment, and the specific step of obtaining the forest type fire risk index in the first step includes:
step one, acquiring the number of refractory tree species in a monitoring area;
step two, acquiring the total number of trees in a monitoring area;
step three, the quotient of the quantity of the refractory tree species obtained in the step one and the total quantity of the forest trees obtained in the step two is obtained to obtain the proportion of the refractory tree species;
and step four, obtaining the forest type fire danger index according to the proportion of the refractory tree types obtained in the step three and by using the first inverse proportion decreasing function as an evaluation function of the forest type fire danger index.
In the present embodiment, since the first inverse proportional decreasing function is used as the evaluation function of the forest species fire risk index, the forest density fire risk index becomes lower as the proportion of the refractory tree species increases.
The third concrete implementation mode: in this embodiment, the forest fire prevention level prediction algorithm based on community characteristics described in the second embodiment is further limited, and in this embodiment, the specific step of obtaining the forest stand density fire risk index in the third step includes:
step three, acquiring the total area of a monitoring area;
step two, obtaining the forest stand density of the monitoring area by utilizing the quotient of the total quantity of the forest trees obtained in the step one and the total area of the monitoring area obtained in the step three;
and thirdly, obtaining the forest stand density fire danger index according to the forest stand density obtained in the third step two and by using a second inverse proportion decreasing function as an evaluation function of the forest stand density fire danger index.
In the present embodiment, since the second inverse proportional decreasing function is adopted as the evaluation function of the forest stand density fire risk index, the greater the forest stand density is, the lower the forest stand density fire risk index is.
The fourth concrete implementation mode: in this embodiment, the forest fire-prevention-level prediction algorithm based on community characteristics is further defined in the first embodiment, and the specific step of obtaining the average age fire risk index in the second step includes:
step two, randomly selecting N sample areas in a monitoring area;
step two, acquiring the number of the trees in each sample area and acquiring the age of the trees in each sample area;
step two, dividing the total of the tree ages in the same sample area by the number of the trees, and calculating for N times to obtain the average tree age of each sample area;
step two, accumulating the average tree age of each sample area obtained in the step two, obtaining the quotient of the accumulated result and N, obtaining the average tree age of the N sample areas, and representing the average tree age of the monitoring area by the average tree age of the N sample areas; n is a positive integer greater than 2;
and step two, obtaining the average tree age fire risk index according to the average tree age of the monitoring area obtained in the step two and by using the parabolic function with the upward opening as the evaluation function of the average tree age fire risk index.
In this embodiment, the average tree age of the monitored area is obtained by a random sampling statistical method, taking randomly selecting 5 sample areas as an example, the 5 sample areas respectively select east, west, south, north and center differences of the monitored area, the selected areas are 8 square meters, adding the tree ages of all the selected trees within 8 square meters together, and making a quotient with the number of the trees within 8 square meters to obtain the average tree age of the sample area, calculating 5 times to obtain 5 sample areasThe average age of the trees in this region is A1、A2、A3、A4And A5The mean age of the 5 sample regions is shown
Wherein the content of the first and second substances,
represents the average tree age of 5 sample regions.
In the embodiment, because a parabolic function with an upward opening is used as an evaluation function of the average tree age fire risk index, it can be determined that the young trees have poor branch and leaf flourishing properties, so the average tree age fire risk index is higher, the middle-aged trees have good branch and leaf flourishing properties, and the trees have high water content, so the average tree age fire risk index is lower; the moisture content of mature forest trees is reduced, so the average tree age fire risk index is higher.
The fifth concrete implementation mode: in this embodiment, the forest fire-prevention-level prediction algorithm based on community characteristics according to the first embodiment is further defined, and in this embodiment, the specific step of obtaining the weather monitoring fire risk index in the fourth step is as follows:
step four, acquiring meteorological monitoring data of a monitoring area through a meteorological station;
taking the day as a sample unit, and selecting a fire sample as a modeling sample according to the meteorological monitoring data acquired in the step four;
step four, acquiring a meteorological factor corresponding to the modeling sample in the step four;
fourthly, constructing a single classification SVM model based on meteorological factors corresponding to the modeling samples in the fourth step and the third step;
and step four, mapping the value range of the distance from the sample output in the middle of the single classification SVM model constructed in the step four to the spherical center of the hypersphere in the model to [0,1] by using an activation function, wherein the mapping result is the meteorological monitoring fire risk index.
In the embodiment, the single classification SVM model takes a plurality of meteorological factors as influence factors for judging the meteorological monitoring fire risk index, and learns a forest fire risk occurrence probability model based on the single classification SVM by using a sample without fire occurrence so as to obtain the meteorological monitoring fire risk index; the problem of unbalanced classification caused by concentrated forest fire samples is effectively solved; the forest fire danger grade is judged from the perspective of the fire occurrence probability, and the accuracy of judging the forest fire danger is improved.
The sixth specific implementation mode: in this embodiment, the forest fire prevention level prediction algorithm based on community characteristics described in the fifth embodiment is further defined, and in this embodiment, the activation function used in the fourth and fifth steps adopts:
in the present embodiment, an activation function is used
Mapping the value range of the distance from the sample of the middle output of the single classification SVM model constructed in the fourth step to the spherical center of the hypersphere in the model to [0,1]And the mapping result is the weather monitoring fire risk index.
The seventh embodiment: in the embodiment, the forest fire prevention grade prediction algorithm based on community characteristics in the first embodiment is further limited, and in the sixth embodiment, when the forest fire prevention grade is predicted according to the comprehensive fire risk index, the following principle is followed:
when the comprehensive fire danger index is [0, 0.8], predicting the forest fire prevention grade as the first level of fire danger;
when the comprehensive fire danger index is (0.8, 1.6), predicting the forest fire prevention grade as the fire danger second grade;
when the comprehensive fire danger index is (1.6, 2.4), predicting the forest fire prevention grade to be three levels of fire danger;
when the comprehensive fire danger index is (2.4, 3.2), predicting the forest fire prevention grade to be a fire danger level four;
and when the comprehensive fire danger index is in (3.2, 4), predicting the forest fire prevention grade to be fire danger five grade.
In the embodiment, in order to adapt to the habits of fire prevention command departments and the public in applying fire prediction, the fire degree of the forest is artificially divided into five fire grades, which are specifically shown in table 1.
Watch 1
| Fire hazard class | Degree of danger | Degree of flammability | Degree of spread |
| A | Without danger | Can not burn | Can not spread |
| II | Low risk | Is difficult to burn | Is difficult to spread |
| III | Moderate risk | Is easier to burn | Is easy to spread |
| Fourthly | High risk | Easy to burn | Is easy to spread |
| Five of them | Extreme danger | Is extremely easy to burn | Is very easy to spread |
。
Claims (7)
1. A forest fire prevention grade prediction algorithm based on community characteristics is characterized in that the forest fire prevention grade prediction algorithm is used for predicting the fire prevention grade of a monitored area;
the forest fire prevention grade prediction algorithm comprises the following steps:
step one, acquiring the proportion of fire-resistant tree species in the tree species in a monitoring area, and obtaining the fire risk index of the tree species according to the proportion of the fire-resistant tree species;
step two, obtaining the average tree age of the monitoring area, and obtaining an average tree age fire risk index according to the average tree age;
step three, acquiring the forest stand density of the monitoring area, and obtaining a forest stand density fire risk index according to the forest stand density;
acquiring meteorological monitoring data of a monitoring area, and obtaining a meteorological monitoring fire risk index according to the meteorological monitoring data;
step five, the forest type fire risk index obtained in the step one is simultaneously summed with the average tree age fire risk index obtained in the step two, the forest stand density fire risk index obtained in the step three and the weather monitoring fire risk index obtained in the step four to obtain a comprehensive fire risk index;
and step six, predicting the forest fire prevention grade according to the comprehensive fire danger index obtained in the step five.
2. A forest fire prevention grade prediction algorithm based on community characteristics as claimed in claim 1, wherein the specific step of obtaining the forest category fire risk index in the first step comprises:
step one, acquiring the number of refractory tree species in a monitoring area;
step two, acquiring the total number of trees in a monitoring area;
step three, the quotient of the quantity of the refractory tree species obtained in the step one and the total quantity of the forest trees obtained in the step two is obtained to obtain the proportion of the refractory tree species;
and step four, obtaining the forest type fire danger index according to the proportion of the refractory tree types obtained in the step three and by using the first inverse proportion decreasing function as an evaluation function of the forest type fire danger index.
3. A forest fire prevention grade prediction algorithm based on community characteristics as claimed in claim 2, wherein the specific step of obtaining the forest stand density fire risk index in the third step comprises:
step three, acquiring the total area of a monitoring area;
step two, obtaining the forest stand density of the monitoring area by utilizing the quotient of the total quantity of the forest trees obtained in the step one and the total area of the monitoring area obtained in the step three;
and thirdly, obtaining the forest stand density fire danger index according to the forest stand density obtained in the third step two and by using a second inverse proportion decreasing function as an evaluation function of the forest stand density fire danger index.
4. A forest fire prevention grade prediction algorithm based on community characteristics as claimed in claim 1, wherein the specific step of obtaining the average age fire risk index in the second step comprises:
step two, randomly selecting N sample areas in a monitoring area;
step two, acquiring the number of the trees in each sample area and acquiring the age of the trees in each sample area;
step two, dividing the total of the tree ages in the same sample area by the number of the trees, and calculating for N times to obtain the average tree age of each sample area;
step two, accumulating the average tree age of each sample area obtained in the step two, obtaining the quotient of the accumulated result and N, obtaining the average tree age of the N sample areas, and representing the average tree age of the monitoring area by the average tree age of the N sample areas; n is a positive integer greater than 2;
and step two, obtaining the average tree age fire risk index according to the average tree age of the monitoring area obtained in the step two and by using the parabolic function with the upward opening as the evaluation function of the average tree age fire risk index.
5. A forest fire prevention grade prediction algorithm based on community characteristics as claimed in claim 1, wherein the specific steps of obtaining the weather monitoring fire risk index in the fourth step are as follows:
step four, acquiring meteorological monitoring data of a monitoring area through a meteorological station;
taking the day as a sample unit, and selecting a fire sample as a modeling sample according to the meteorological monitoring data acquired in the step four;
step four, acquiring a meteorological factor corresponding to the modeling sample in the step four;
fourthly, constructing a single classification SVM model based on meteorological factors corresponding to the modeling samples in the fourth step and the third step;
and step four, mapping the value range of the distance from the sample output in the middle of the single classification SVM model constructed in the step four to the spherical center of the hypersphere in the model to [0,1] by using an activation function, wherein the mapping result is the meteorological monitoring fire risk index.
6. A forest fire prevention grade prediction algorithm based on community characteristics as claimed in claim 5, characterized in that the activation function used in the fourth and fifth steps adopts:
7. a forest fire prevention grade prediction algorithm based on community characteristics as claimed in claim 1, wherein in the sixth step, when the forest fire prevention grade is predicted according to the comprehensive fire danger index, the following principle is followed:
when the comprehensive fire danger index is [0, 0.8], predicting the forest fire prevention grade as the first level of fire danger;
when the comprehensive fire danger index is (0.8, 1.6), predicting the forest fire prevention grade as the fire danger second grade;
when the comprehensive fire danger index is (1.6, 2.4), predicting the forest fire prevention grade to be three levels of fire danger;
when the comprehensive fire danger index is (2.4, 3.2), predicting the forest fire prevention grade to be a fire danger level four;
and when the comprehensive fire danger index is in (3.2, 4), predicting the forest fire prevention grade to be fire danger five grade.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110244701.XA CN112990562A (en) | 2021-03-05 | 2021-03-05 | Forest fire prevention grade prediction algorithm based on community characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110244701.XA CN112990562A (en) | 2021-03-05 | 2021-03-05 | Forest fire prevention grade prediction algorithm based on community characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112990562A true CN112990562A (en) | 2021-06-18 |
Family
ID=76352991
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110244701.XA Pending CN112990562A (en) | 2021-03-05 | 2021-03-05 | Forest fire prevention grade prediction algorithm based on community characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112990562A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114005237A (en) * | 2021-10-30 | 2022-02-01 | 南京林业大学 | Forest fire identification method and equipment based on thermal imaging analysis technology and computer storage medium |
| CN114442198A (en) * | 2022-01-21 | 2022-05-06 | 广西壮族自治区气象科学研究所 | Forest fire weather grade forecasting method based on weighting algorithm |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620451A (en) * | 2008-06-30 | 2010-01-06 | 中国林业科学研究院森林生态环境与保护研究所 | Quick search ruler for forest fire danger classes |
| CN103824138A (en) * | 2012-11-19 | 2014-05-28 | 郭志华 | Forest fire hazard emergency command decision management GIS three-dimensional platform |
| CN107085904A (en) * | 2017-03-31 | 2017-08-22 | 上海事凡物联网科技有限公司 | Forest fire danger class decision method and system based on single classification SVM |
-
2021
- 2021-03-05 CN CN202110244701.XA patent/CN112990562A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101620451A (en) * | 2008-06-30 | 2010-01-06 | 中国林业科学研究院森林生态环境与保护研究所 | Quick search ruler for forest fire danger classes |
| CN103824138A (en) * | 2012-11-19 | 2014-05-28 | 郭志华 | Forest fire hazard emergency command decision management GIS three-dimensional platform |
| CN107085904A (en) * | 2017-03-31 | 2017-08-22 | 上海事凡物联网科技有限公司 | Forest fire danger class decision method and system based on single classification SVM |
Non-Patent Citations (1)
| Title |
|---|
| 陈家兴: "南京老山林场地表可燃物载量及火险等级划分研究", 《中国优秀硕士学位论文全文数据库 农业科技辑》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114005237A (en) * | 2021-10-30 | 2022-02-01 | 南京林业大学 | Forest fire identification method and equipment based on thermal imaging analysis technology and computer storage medium |
| CN114005237B (en) * | 2021-10-30 | 2023-03-28 | 南京林业大学 | Forest fire identification method and equipment based on thermal imaging analysis technology and computer storage medium |
| CN114442198A (en) * | 2022-01-21 | 2022-05-06 | 广西壮族自治区气象科学研究所 | Forest fire weather grade forecasting method based on weighting algorithm |
| CN114442198B (en) * | 2022-01-21 | 2024-03-15 | 广西壮族自治区气象科学研究所 | Forest fire weather grade forecasting method based on weighting algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113313384B (en) | Urban flood disaster risk assessment method integrating elasticity | |
| Barot et al. | Demography of a savanna palm tree: predictions from comprehensive spatial pattern analyses | |
| CN112990562A (en) | Forest fire prevention grade prediction algorithm based on community characteristics | |
| Sun et al. | Coupled impacts of climate and land use changes on regional ecosystem services | |
| CN106845080B (en) | Based on the modified Scene Tourist meteorological disaster intelligent Forecasting of difference | |
| CN103155836B (en) | Method for forecasting forest pest occurrence degree | |
| Fan et al. | Risk assessment of drought in the Yangtze River Delta based on natural disaster risk theory | |
| Tri et al. | Application of meteorological and hydrological drought indices to establish drought classification maps of the Ba River Basin in Vietnam | |
| CN109784720B (en) | Power distribution network risk assessment method based on space-time grid association under typhoon disaster | |
| CN106548439A (en) | A kind of system for residential quarters Ecology Environment Evaluation | |
| Rego et al. | Climatic patterns in the Mediterranean region | |
| Silveira et al. | Streamflow projections for the Brazilian hydropower sector from RCP scenarios | |
| Southey | Wildfires in the Cape Floristic Region: Exploring vegetation and weather as drivers of fire frequency | |
| Williams et al. | Studies in the Numerical Analysis of Complex Rain-Forest Communities: VI. Models for the Classification of Quantitative Data | |
| CN108694247B (en) | Typhoon disaster analysis method based on microblog topic popularity | |
| Guo et al. | Place vulnerability assessment based on the HOP model in the middle and lower reaches of the Yangtze River | |
| CN113469518A (en) | RBF neural network-based rural house typhoon disaster estimation method | |
| CN110969303B (en) | Tree height prediction method based on rational Charles model | |
| Terassi et al. | Analysis of daily rainfall and spatiotemporal trends of extreme rainfall at Paraná slope of the Itararé watershed, Brazil | |
| Wang | Feasibility study of typhoon disaster economic loss assessment based on random forest | |
| de Souza et al. | Spatial and temporal variability of pluviometric precipitation in the hydrographic region of Paraguaçu-BA | |
| Zeng et al. | Flood risk assessment based on principal component analysis for Dongjiang river basin | |
| Araujo et al. | Climatic characterization and temporal analysis of rainfall in the municipality of Cruzeiro do Sul-AC, Brazil | |
| CN113469582B (en) | Multi-level typhoon disaster risk assessment method | |
| de Lima Barros et al. | Influence of rainfall on wind power generation in Northeast Brazil |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210618 |
|
| RJ01 | Rejection of invention patent application after publication |